28 research outputs found
Smartphone Based Image Color Correction for Color Blindness
No full textColor blind is a type of Color Vision Deficiency, which is the inability that a person could not realize the differences between some colors. There are three types of color blindness: Monochromacy, Dichromacy, and Anomalous Trichromacy. Color blind cannot be cured. Today, technology gets up with solutions to help people with color blindness to see the image and distinguish between the different colors using some algorithms. This paper presents a smartphone based experimental comparison of color correction algorithms for all Dichromacy color-blind viewers: Protanopia, Duteranopia, and Tritanopia. This comparison includes LMS Daltonization algorithm, Color-blind Filter Service (CBFS) algorithm, LAB color corrector algorithm, and the shifting color algorithm. The LMS algorithm is implemented for all the three types of Dichromacy. While CBFS, LAB adjustment, and Shifting color algorithms are applied to correct colors for Protanopia, Duteranopia, and Tritanopia respectively. The results show that the processing time for LMS algorithm is slow compared to other algorithms. For Protanopia people, the LMS algorithm is better than CBFS algorithm as the LMS algorithm only changes color of con-fused areas with no change in the brightness. For Duteranopia people, the LAB color correction is better than the LMS algorithm. For Tritanopia people, both the shifting color algorithm and the LMS algorithm may produce a new confu-sion in the proceed images. An application interface is implemented to enable the user to choose the algorithm that gives the most appropriate results
Biometric Template Protection for Dynamic Touch Gestures Based on Fuzzy Commitment Scheme and Deep Learning
No full textPrivacy plays an important role in biometric authentication systems. Touch authentication systems have been widely used since touch devices reached their current level of development. In this work, a fuzzy commitment scheme (FCS) is proposed based on deep learning (DL) to protect the touch-gesture template in a touch authentication system. The binary Bose–Ray-Chaudhuri code (BCH) is used with FCS to deal with touch variations. The BCH code is described by the triplet (n, k, t) where n denotes the code word’s length, k denotes the length of the key and t denotes error-correction capability. In our proposed system, the system performance is investigated using different lengths k. The learning-based approach is applied to extract touch features from raw touch data, as the recurrent neural network (RNN) is used based on a convolutional neural network (CNN). The proposed system has been evaluated on two different touch datasets: the Touchalytics dataset and BioIdent dataset. The best results obtained were with a key length k = 99 and n = 255; the false accept rate (FAR) was 0.00 and false reject rate (FRR) was 0.5854 for the Touchalytics dataset, while the FAR was 0.00 and FRR was 0.5399 with the BioIdent dataset. The FCS shows its effectiveness in dynamic authentication systems, as good results are obtained and compared with other works
A Weighted Score Matching Algorithm for a Multimodal Biometric System Based on Fingerprint and Hand Geometry.
No full text
Automated Fingerprint Identification System based on weighted feature points matching algorithm
No full textMachine vision gait-based biometric cryptosystem using a fuzzy commitment scheme
No full textIn this paper, a fuzzy commitment scheme is applied with a machine vision gait-based biometric system to enhance system security. The proposed biometric cryptosystem has two phases: enrolment and verification. Each of them comprises three main stages: feature extraction, reliable components extraction, and fuzzy commitment scheme. Gait features are extracted from gait images using local ternary pattern (LTP), and then, the average of one complete gait cycle using the gait energy image (GEl) concept is calculated. The average images are joined using a 2D joint histogram, which is reduced using principal component analysis (PCA) to produce the final feature vector. To enhance the robustness of the system, only highly robust and reliable bits from the feature vector are extracted. Finally, the fuzzy commitment scheme is used to secure feature templates. Bose–Chaudhuri–Hocquenghem codes (BCH) are used for key encoding in the enrolment phase and for decoding in the verification phase. The proposed system is tested using the CMU MoBo and CASIA A databases. The experimental results show that the best error rate for the CMU MoBo database is obtained when using a fast walk for enrolment and verification, where we obtain 0% for the false acceptance rate (FAR) and 0% for the false rejection rate (FRR) for a key length equal to 50 bits. The best error rate for CASIA A dataset is obtained when using the 45-degree direction to the image plane view for enrolment and verification, where we obtain 0% for the false acceptance rate (FAR) and 0% for the false rejection rate (FRR) for a key length equal to 45 bits
An Ensemble Machine Learning Technique for Functional Requirement Classification
No full textIn Requirement Engineering, software requirements are classified into two main categories: Functional Requirement (FR) and Non-Functional Requirement (NFR). FR describes user and system goals. NFR includes all constraints on services and functions. Deeper classification of those two categories facilitates the software development process. There are many techniques for classifying FR; some of them are Machine Learning (ML) techniques, and others are traditional. To date, the classification accuracy has not been satisfactory. In this paper, we introduce a new ensemble ML technique for classifying FR statements to improve their accuracy and availability. This technique combines different ML models and uses enhanced accuracy as a weight in the weighted ensemble voting approach. The five combined models are Naïve Bayes, Support Vector Machine (SVM), Decision Tree, Logistic Regression, and Support Vector Classification (SVC). The technique was implemented, trained, and tested using a collected dataset. The accuracy of classifying FR was 99.45%, and the required time was 0.7 s
One- and Two-Phase Software Requirement Classification Using Ensemble Deep Learning
No full textRecently, deep learning (DL) has been utilized successfully in different fields, achieving remarkable results. Thus, there is a noticeable focus on DL approaches to automate software engineering (SE) tasks such as maintenance, requirement extraction, and classification. An advanced utilization of DL is the ensemble approach, which aims to reduce error rates and learning time and improve performance. In this research, three ensemble approaches were applied: accuracy as a weight ensemble, mean ensemble, and accuracy per class as a weight ensemble with a combination of four different DL models—long short-term memory (LSTM), bidirectional long short-term memory (BiLSTM), a gated recurrent unit (GRU), and a convolutional neural network (CNN)—in order to classify the software requirement (SR) specification, the binary classification of SRs into functional requirement (FRs) or non-functional requirements (NFRs), and the multi-label classification of both FRs and NFRs into further experimental classes. The models were trained and tested on the PROMISE dataset. A one-phase classification system was developed to classify SRs directly into one of the 17 multi-classes of FRs and NFRs. In addition, a two-phase classification system was developed to classify SRs first into FRs or NFRs and to pass the output to the second phase of multi-class classification to 17 classes. The experimental results demonstrated that the proposed classification systems can lead to a competitive classification performance compared to the state-of-the-art methods. The two-phase classification system proved its robustness against the one-phase classification system, as it obtained a 95.7% accuracy in the binary classification phase and a 93.4% accuracy in the second phase of NFR and FR multi-class classification
